Short-Term Forecasting of Power Production in a Large-Scale Photovoltaic Plant Based on LSTM
Source abstract
Abstract
Photovoltaic (PV) power is attracting more and more concerns. Power output prediction, as a necessary technical requirement of PV plants, closely relates to the rationality of power grid dispatch. If the accuracy of power prediction in PV plants can be further enhanced by forecasting, stability of power grid will be improved. Therefore, a 1-h-ahead power output forecasting based on long-short-term memory (LSTM) networks is proposed. The forecasting output of the model is based on the time series of 1-h-ahead numerical weather prediction to reveal the spatio-temporal characteristic. The comprehensive meteorological conditions, including different types of season and weather conditions, were considered in the model, and parameters of LSTM models were investigated simultaneously. Analysis of prediction result reveals that the proposed model leads to a superior prediction performance compared with traditional PV output power predictions. The accuracy of output power prediction is enhanced by 3.46–13.46%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Solar Radiation and Photovoltaics · Photovoltaic System Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
China Academy of Aerospace Standardization and Product Assurance, Beijing 100071, China
Funding
the Fundamental Research Funds for the Central Universities
References (31)
Show source-provided references
1. Optimal capacity design of battery and hydrogen system for the DC grid with photovoltaic power generation based on the rapid estimation of grid dependency10.1016/j.ijepes.2016.12.012 ↗
2. A critical review of electric vehicle charging using solar photovoltaic10.1002/er.3472 ↗
3. Joint optimal operation of photovoltaic units and electric vehicles in residential networks with storage systems: A dynamic scheduling method10.1016/j.ijepes.2018.05.015 ↗
4. Progress in new semiconductor materials classes for solar photoelectrolysis10.1002/er.1660 ↗
5. Short-term forecasting of power production in a large-scale photovoltaic plant10.1016/j.solener.2014.03.018 ↗
6. Physical and hybrid methods comparison for the day ahead PV output power forecast10.1016/j.renene.2017.05.063 ↗
7. An artificial neural network to assess the impact of neighbouring photovoltaic systems in power forecasting in Utrecht, The Netherlands10.1016/j.renene.2015.06.061 ↗
8. Short-term solar power forecasting considering cloud coverage and ambient temperature variation effects10.1016/j.renene.2018.02.102 ↗
9. Short-term predictability of photovoltaic production over Italy10.1016/j.renene.2015.02.010 ↗
10. PV power conversion and short-term forecasting in a tropical, densely-built environment in Singapore10.1016/j.renene.2016.03.075 ↗
11. Improved near surface wind speed predictions using Gaussian process regression combined with numerical weather predictions and observed meteorological data10.1016/j.renene.2018.04.019 ↗
12. Huang, R., Huang, T., and Gadh, R. (2012, January 5–8). Solar generation prediciton using the ARMA model in a laboratory-level micro-grid. Proceedings of the IEEE SmartGridComm 2012 Symposium—Support for Storage, Renewable Sources, and MicroGrid, Tainan, Taiwan.10.1109/SmartGridComm.2012.6486039 ↗
13. Smart energy management system for optimal microgrid economic operation10.1049/iet-rpg.2010.0052 ↗
14. Performance evaluation and accuracy enhancement of a day-ahead wind power forecasting system in China10.1016/j.renene.2011.11.051 ↗
15. Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines10.1109/TIA.2012.2190816 ↗
16. Forecasting Power Output of Solar Photovoltaic System Using Wavelet Transform and Artificial Intelligence Techniques10.1016/j.procs.2012.09.080 ↗
17. Machine learning for solar irradiance forecasting of photovoltaic system10.1016/j.renene.2015.12.069 ↗
18. Learning precise timing with LSTM recurrent networks
19. Wind power prediction using deep neural network based meta regression and transfer learning10.1016/j.asoc.2017.05.031 ↗
20. Learning long-term dependencies with gradient descent is difficult10.1109/72.279181 ↗
21. Representation Learning: A Review and New Perspectives10.1109/TPAMI.2013.50 ↗
22. Almeida, A., and Azkune, G. (2018). Predicting Human Behaviour with Recurrent Neural Networks. Appl. Sci., 8.10.3390/app8020305 ↗
23. Short-term residential load forecasting based on LSTM recurrent neural network10.1109/TSG.2017.2753802 ↗
24. Wavelet decomposition and convolutional LSTM networks based improved deep learning model for solar irradiance forecasting10.3390/app8081286 ↗
25. Gensler, A., Henze, J., Sick, B., and Raabe, N. (2016, January 9–12). Deep Learning for solar power forecasting—An approach using AutoEncoder and LSTM Neural Networks. Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary.10.1109/SMC.2016.7844673 ↗
26. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
27. SW-ELM: A summation wavelet extreme learning machine algorithm with a priori parameter initialization10.1016/j.neucom.2013.07.021 ↗
28. Time series forecasting with neural networks: A comparative study using the airline data
29. An architecture for emergency event prediction using LSTM recurrent neural networks10.1016/j.eswa.2017.12.037 ↗
30. Kingma, D.P., and Jimmy, L.B. (2015). Adma: A method for stochastic optimization. ICLR, Arxiv.Org.
31. Dropout: A simple way to prevent neural networks from overfitting